© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19413
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scribers
    -0.09
    scriber
    -0.09
    sburg
    -0.08
    урнал
    -0.08
     basin
    -0.08
    auche
    -0.07
    -Cola
    -0.07
     memiliki
    -0.07
     אלו
    -0.07
     Basin
    -0.07
    POSITIVE LOGITS
    ally
    0.10
    ically
    0.09
     भावना
    0.09
     cảm
    0.08
     ощущ
    0.08
     изображения
    0.08
    감을
    0.08
     emoção
    0.08
    .expression
    0.08
    感
    0.08
    Activations Density 0.005%

    No Known Activations